Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Stochastic Optimisation Framework using the Core Imaging Library and Synergistic Image Reconstruction Framework for PET Reconstruction

Evangelos Papoutsellis, Casper da Costa-Luis, Daniel Deidda, Claire Delplancke, Margaret Duff, Gemma Fardell, Ashley Gillman, Jakob S. Jørgensen, Zeljko Kereta, Evgueni Ovtchinnikov, Edoardo Pasca, Georg Schramm, Kris Thielemans

TL;DR

It is observed that stochastic optimisation methods can converge in fewer passes of the data than a standard deterministic algorithm.

Abstract

We introduce a stochastic framework into the open--source Core Imaging Library (CIL) which enables easy development of stochastic algorithms. Five such algorithms from the literature are developed, Stochastic Gradient Descent, Stochastic Average Gradient (-Amélioré), (Loopless) Stochastic Variance Reduced Gradient. We showcase the functionality of the framework with a comparative study against a deterministic algorithm on a simulated 2D PET dataset, with the use of the open-source Synergistic Image Reconstruction Framework. We observe that stochastic optimisation methods can converge in fewer passes of the data than a standard deterministic algorithm.

Stochastic Optimisation Framework using the Core Imaging Library and Synergistic Image Reconstruction Framework for PET Reconstruction

TL;DR

It is observed that stochastic optimisation methods can converge in fewer passes of the data than a standard deterministic algorithm.

Abstract

We introduce a stochastic framework into the open--source Core Imaging Library (CIL) which enables easy development of stochastic algorithms. Five such algorithms from the literature are developed, Stochastic Gradient Descent, Stochastic Average Gradient (-Amélioré), (Loopless) Stochastic Variance Reduced Gradient. We showcase the functionality of the framework with a comparative study against a deterministic algorithm on a simulated 2D PET dataset, with the use of the open-source Synergistic Image Reconstruction Framework. We observe that stochastic optimisation methods can converge in fewer passes of the data than a standard deterministic algorithm.
Paper Structure (42 sections, 17 equations, 1 figure, 1 table)

This paper contains 42 sections, 17 equations, 1 figure, 1 table.

Table of Contents

  1. Introduction
  2. The Design, Intent and Limitations of the Templates
  3. LaTeX Distributions: Where to Get Them
  4. Where to get the IEEEtran Templates
  5. Where to get LaTeX help - user groups
  6. Document Class Options in IEEEtran
  7. How to Create Common Front Matter
  8. Paper Title
  9. Author Names and Affiliations
  10. Running Heads
  11. Copyright Line
  12. Abstracts
  13. Index Terms
  14. How to Create Common Body Elements
  15. Initial Drop Cap Letter
  16. ...and 27 more sections

Figures (1)

  • Figure 1: This is the caption for one fig.